Related papers: Toward Self-Adjusting k-ary Search Tree Networks
A self-organization of efficient and robust networks is important for a future design of communication or transportation systems, however both characteristics are incompatible in many real networks. Recently, it has been found that the…
In the next generation network, the satellite network will play a fundamental role, in overcoming the limitation of the terrestrial network. Nonetheless, the satellite-terrestrial network integration presents a number of problems due to the…
Discretization based approaches to solving online reinforcement learning problems have been studied extensively in practice on applications ranging from resource allocation to cache management. Two major questions in designing…
Recently, Neural Architecture Search (NAS) methods have been introduced and show impressive performance on many benchmarks. Among those NAS studies, Neural Architecture Transformer (NAT) aims to adapt the given neural architecture to…
Most computational models of dependency syntax consist of distributions over spanning trees. However, the majority of dependency treebanks require that every valid dependency tree has a single edge coming out of the ROOT node, a constraint…
A mechanism for self-organization of the degree of connectivity in model neural networks is studied. Network connectivity is regulated locally on the basis of an order parameter of the global dynamics which is estimated from an observable…
High sensitivity of neural architecture search (NAS) methods against their input such as step-size (i.e., learning rate) and search space prevents practitioners from applying them out-of-the-box to their own problems, albeit its purpose is…
Most deployed WAN Traffic Engineering (TE) systems use a logically centralized controller that periodically gathers traffic demands, runs a TE optimization or heuristic, and then programs the network. At scale, these solutions can be…
The network reconfiguration problem seeks to find a rooted tree $T$ such that the energy of the (unique) feasible electrical flow over $T$ is minimized. The tree requirement on the support of the flow is motivated by operational constraints…
Kinodynamic motion planning is concerned with computing collision-free trajectories while abiding by the robot's dynamic constraints. This critical problem is often tackled using sampling-based planners (SBPs) that explore the robot's…
Nodes in route-restricted overlays have an immutable set of neighbors, explicitly specified by their users. Popular examples include payment networks such as the Lightning network as well as social overlays such as the Dark Freenet. Routing…
Geo-distributed analytics (GDA) frameworks transfer large datasets over the wide-area network (WAN). Yet existing frameworks often ignore the WAN topology. This disconnect between WAN-bound applications and the WAN itself results in missed…
Autonomous driving platforms encounter diverse driving scenarios, each with varying hardware resources and precision requirements. Given the computational limitations of embedded devices, it is crucial to consider computing costs when…
One of the most exciting advancements in AI over the last decade is the wide adoption of ANNs, such as DNN and CNN, in many real-world applications. However, the underlying massive amounts of computation and storage requirement greatly…
We propose Kevin, a novel demand-aware reconfigurable rack-to-rack datacenter network realized with a simple and efficient control plane. In particular, Kevin makes effective use of the network capacity by supporting integrated and…
A skip graph is a resilient application-layer routing structure that supports range queries of distributed k-dimensional data. By sorting deterministic keys into groups based on locally computed random membership vectors, nodes in a…
Network science has traditionally examined how structure determines dynamics. Here we invert this paradigm: we ask how functional dynamics and resource constraints shape network architecture. We introduce GradNet, an AI-enabled optimization…
Recurrent spiking neural networks (RSNNs) are a promising substrate for energy-efficient control policies, but training them for high-dimensional, long-horizon reinforcement learning remains challenging. Population-based, gradient-free…
Datacenter network design plays a critical role in AI training by supporting scaling to thousands of accelerators. An open problem, designing a near-optimal throughput oriented network-topology, routing, and collectives-has not been…
This paper shows that a new type of artificial neural network (ANN) -- the Simultaneous Recurrent Network (SRN) -- can, if properly trained, solve a difficult function approximation problem which conventional ANNs -- either feedforward or…